© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15736
    Prev
    Next
    INDEX
    Explanations

    def bagging classifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मलिक
    0.39
    orduk
    0.38
    Dere
    0.37
    LPTMR
    0.37
     aw
    0.36
     harbour
    0.36
    ollo
    0.36
     õ
    0.35
     детства
    0.35
    тат
    0.34
    POSITIVE LOGITS
     photographing
    0.42
     enforcement
    0.40
    ক্রে
    0.37
     GoPro
    0.36
     journalist
    0.36
     обеспечение
    0.36
     surveillance
    0.36
     Enforcement
    0.35
     female
    0.35
     updating
    0.35
    Activations Density 0.037%

    No Known Activations